Knowledge catalogue
arXiv:2604.07801v1 Announce Type: new Abstract: Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world quer
arXiv:2604.06197v1 Announce Type: cross Abstract: Type 2 diabetes case reports describe complex clinical courses, but their timelines are often expressed in language that is difficult to reuse in long
arXiv:2604.08072v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) excel at extracting local features hierarchically, but their performance in capturing complex correlations hinges h
arXiv:2511.03595v2 Announce Type: replace Abstract: High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-lea
TGIF! Here are some of our favorite updates from the past week: — Notebooks in @GeminiApp, an integration with @NotebookLM that enables you to retrieve context from your private notebooks or convert y
arXiv:2604.06906v1 Announce Type: cross Abstract: As Large Language Models reshape the global labor market, policymakers and workers need empirical data on which occupational skills may be most suscep
arXiv:2604.07190v1 Announce Type: cross Abstract: We present a comprehensive adoption snapshot of the leading open language models and who is building them, focusing on the ~1.5K mainline open models
arXiv:2604.06427v1 Announce Type: cross Abstract: The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is
arXiv:2604.06222v1 Announce Type: cross Abstract: Why do we forget? Why do we remember things that never happened? The conventional answer points to biological hardware. We propose a different one: ge
arXiv:2604.07102v1 Announce Type: cross Abstract: Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study pe
arXiv:2604.06192v1 Announce Type: cross Abstract: Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains largely em
arXiv:2604.07267v1 Announce Type: cross Abstract: Gaussian process (GP) regression is a widely used non-parametric modeling tool, but its cubic complexity in the training size limits its use on mass
arXiv:2604.06724v1 Announce Type: cross Abstract: While traditional optimization problems were often studied in isolation, many real-world problems today require interdependence among multiple optimiz
There were some exceptionally cool demos from @ollama and omlx using MLX to run Qwen 3.5 and Gemma 4 on Apple silicon. The capabilities of local LLMs and the surrounding ecosystem have come a long way
arXiv:2405.08253v3 Announce Type: replace-cross Abstract: This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. Mor
arXiv:2604.06282v1 Announce Type: cross Abstract: We study mean estimation of a random vector X in a distributed parameter-server-worker setup. Worker i observes samples of a_i^op X, where $a_
arXiv:2604.07816v1 Announce Type: new Abstract: Tool learning has emerged as a promising paradigm for large language models (LLMs) to address real-world challenges. Due to the extensive and irregularl
arXiv:2604.06391v1 Announce Type: cross Abstract: Graphs are a central representation in biomedical research, capturing molecular interaction networks, gene regulatory circuits, cell--cell communicati
arXiv:2505.22976v2 Announce Type: replace-cross Abstract: The ability to simulate the world in a spatially consistent manner is a crucial requirements for effective world models. Such a model enables
arXiv:2604.06689v1 Announce Type: new Abstract: Accurate classification requires not only high predictive accuracy but also well-calibrated confidence estimates. Yet, modern deep neural networks (DNNs
arXiv:2512.08410v2 Announce Type: replace Abstract: Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose
arXiv:2604.08362v1 Announce Type: new Abstract: The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain co
arXiv:2604.06264v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled molecular reasoning for property prediction. However, toxicity arises from complex biolog
arXiv:2604.07553v1 Announce Type: new Abstract: This study presents a framework for generating the gold-standard summary fully automatically and reproducibly based on multiple human summaries of Turki
arXiv:2604.07223v1 Announce Type: cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to int
arXiv:2604.08156v1 Announce Type: new Abstract: Rhyme is deceptively intuitive: what is or is not a rhyme is constructed historically, scholars struggle with rhyme classification, and people disagree
arXiv:2604.07894v1 Announce Type: new Abstract: Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preference
Ultraplan, a planning feature in Claude, consumes approximately the same number of tokens and counts against subscription rate limits similarly to standard plan mode. Users should be aware that using
arXiv:2601.21463v2 Announce Type: replace-cross Abstract: Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting
arXiv:2604.08522v1 Announce Type: new Abstract: Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to
arXiv:2604.07264v1 Announce Type: cross Abstract: Operating LEO mega-constellations requires translating high-level operator intents ('reroute financial traffic away from polar links under 80 ms') int
arXiv:2603.15118v2 Announce Type: replace Abstract: We introduce VAREX (VARied-schema EXtraction), a benchmark for evaluating multimodal foundation models on structured data extraction from government
arXiv:2604.06644v1 Announce Type: cross Abstract: As deep learning inference is increasingly deployed in shared and cloud-based settings, a growing concern is input repurposing, in which data submitte
arXiv:2604.06182v1 Announce Type: cross Abstract: Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of
arXiv:2604.08401v1 Announce Type: cross Abstract: In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However
arXiv:2604.06896v1 Announce Type: new Abstract: Epithelial tissues dynamically reshape through local mechanical interactions among cells, a process well captured by vertex models. Yet their many tunab
arXiv:2509.08016v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail le
arXiv:2510.23642v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, e
arXiv:2604.07705v1 Announce Type: new Abstract: Aerial vision-and-language navigation (Aerial VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and autonom
arXiv:2604.06440v1 Announce Type: cross Abstract: Visual prompting (VP) has emerged as a popular method to repurpose pretrained vision models for adaptation to downstream tasks. Unlike conventional mo
arXiv:2604.08509v1 Announce Type: new Abstract: Digital human generation has been studied for decades and supports a wide range of real-world applications. However, most existing systems are passively
arXiv:2604.07634v1 Announce Type: new Abstract: Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core
arXiv:2603.18474v2 Announce Type: replace Abstract: Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training
We pit LlamaParse against frontier models (Opus 4.6, Gemini 3.1 Pro, GPT-5.4) in a live OCR arena. ICYMI: the full workshop is on Youtube! Frontier VLMs are getting quite good at visual understanding,
We worked with @RWSGroup to fine-tune our Command translation model, which improved language and cultural expertise. Now, that model is the “brain” that powers RWS’ Language Weaver AI translation solu
arXiv:2604.06277v1 Announce Type: new Abstract: Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retri
arXiv:2604.06464v1 Announce Type: new Abstract: Conformal prediction provides distribution-free prediction intervals with finite-sample coverage guarantees, and recent work by Snell & Griffiths refra
what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool d
arXiv:2604.06995v1 Announce Type: new Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct s
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not
arXiv:2510.12476v2 Announce Type: replace Abstract: Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this abi
arXiv:2604.06422v1 Announce Type: cross Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adher
arXiv:2604.08281v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of
arXiv:2510.26241v5 Announce Type: replace-cross Abstract: Modern vision-language models (VLMs) excel at many multimodal tasks, yet their grasp of temporal information in video remains weak and has not
arXiv:2604.07834v1 Announce Type: new Abstract: This paper presents an LLM-driven approach for constructing diverse social media datasets to measure and compare loneliness in the caregiver and non-car
Wrapped up the 3-day AI Engineer conference in London. Key takeaways: Planning & verification > implementation. Humans define what to build and validate it works. AI handles the coding. The harness ma
Yet another illustration of why LLMs aren’t even close to being AGI. The world’s best LLMs are still terrible at poker. We put each model into a 200bb heads-up NLHE match against GTO Wizard AI. The be
arXiv:2503.06717v3 Announce Type: replace Abstract: Interactive segmentation uses real-time user inputs, such as mouse clicks, to iteratively refine model predictions. Although not originally designed
A bit over a decade ago, we got fuzzers. A fuzzer is an automated vulnerability-finder that repeatedly runs a target program with semi-random inputs. One particular fuzzer, American Fuzzy Lop, was not
Editor’s note: This blog post outlines Google Cloud’s GPU AI/ML infrastructure reliability strategy, and will be updated with links to new community articles as they appear. As we enter the era of mul